开始正文前先向大家推荐我的YOLO专栏系列。本人持续更新 YOLOv8、YOLO11、YOLO26 等热门模型内容覆盖图像分类、目标检测、实例分割、多目标跟踪、姿态估计与关键点检测重点讲解 小目标检测、注意力机制、特征融合、损失函数改进、自定义数据集训练、消融实验及论文代码复现。同时分享如何使用 OpenAI Codex辅助撰写论文、配置实验环境、调试项目、改进模型和分析实验结果。 专栏目前正在进行限时优惠每周更新 5–7篇最新论文机制、YOLO改进方法和实战教程。订阅后可获得包含本人全部改进方案的代码与配置文件并加入专属技术交流群。我也会定期在群内分享 YOLO论文选题、创新点设计、实验方案、论文写作与投稿发表经验欢迎大家订阅交流一、本文介绍这次给大家带来的改进机制是高效主干网络——EfficientNetV2本文将使用该网络替换YOLOv26原有的特征提取网络。EfficientNetV2在EfficientNetV1复合缩放策略的基础上进一步针对模型训练速度和计算效率进行了优化其不仅继续兼顾网络深度、通道宽度和输入分辨率还引入了更加高效的Fused-MBConv结构在网络浅层使用普通卷积融合原有MBConv中的扩展卷积和深度卷积以减少部分设备上的访存开销并提高实际运行效率。同时EfficientNetV2提出了改进的渐进式学习策略在训练过程中逐步增大输入图像尺寸并根据图像尺寸自适应调整数据增强和正则化强度从而在保持模型精度的同时加快训练收敛。相较于V1版本EfficientNetV2的主要改进集中在训练速度、参数效率和硬件运行性能方面不过经过本人实际测试当前使用的V2版本速度并没有明显快于V1部分情况下甚至更慢这可能与所选择的模型规模、输入尺寸、硬件平台以及部署环境不同有关因此建议大家选择参数量和计算量接近的版本进行公平对比。EfficientNetV2同样提供S、M、L等多种规模大家可以根据显存条件、数据集难度和实际任务需求在源码中灵活选择。本文将首先介绍EfficientNetV2的整体框架、Fused-MBConv和渐进式学习策略随后结合完整代码与配置文件手把手讲解如何完成模块注册、网络配置以及YOLOv26特征提取网络的替换。本文内容可根据yolov11的N、S、M、L、X进行二次缩放轻量化更上一层。专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制目录一、本文介绍二、EfficientNetV2的框架原理三、EfficientNetV2的核心代码四、手把手教你添加EfficientNetV2机制4.1 修改一4.2 修改二4.3 修改三4.4 修改四4.5 修改五4.6 修改六4.7 修改七4.8 修改八4.9 修改九五、EfficientNetV2的yaml文件5.1 EfficientNetV2的yaml文件5.2 训练文件的代码六、成功运行记录七、本文总结二、EfficientNetV2的框架原理官方论文地址官方论文地址点击即可跳转官方代码地址官方代码地址点击即可跳转这篇论文主要介绍了EfficientNetV2这是一种新型的卷积神经网络它的特点是训练速度更快、参数效率更高。通过结合训练感知的神经架构搜索和缩放这些模型在训练速度和参数效率上都得到了优化。文章还提出了一种改进的渐进式学习方法通过在训练过程中逐步增加图像尺寸并适应性调整正则化来加快训练速度同时保持准确性。EfficientNetV2的主要创新点包括1. 结构创新EfficientNetV2在早期层中采用了fused-MBConv结构这有助于降低内存访问开销。此外EfficientNetV2倾向于使用较小的扩展比例和3x3的卷积核大小同时增加更多的层次来补偿由于使用较小卷积核导致的接收域减小。最后EfficientNetV2完全移除了原始EfficientNet中的最后一个stride-1阶段可能是因为它的大参数尺寸和内存访问开销。2. 训练速度的优化您的研究比较了EfficientNetV2与其他模型在固定图像大小下的训练步骤时间。EfficientNetV2通过训练感知的神经架构搜索和模型缩放实现了比其他最新模型更快的训练速度。3.渐进式学习与自适应正则化EfficientNetV2采用了改进的渐进式学习方法该方法在训练早期使用较小的图像尺寸和较弱的正则化使得网络可以更容易、更快地学习简单的表示。随着训练的进行逐渐增加图像尺寸并通过增强正则化来提高学习难度。4. 自适应正则化的重要性您的研究强调了自适应正则化的重要性这种方法根据图像大小动态调整正则化强度。该方法简单但有效并且可以与其他方法结合使用。图片展示了两种卷积神经网络中的模块MBConv和Fused-MBConv的结构。MBConv这是一种包含了深度可分离卷积depthwise conv3x3的模块其包括1x1的卷积用于调整通道数随后是深度可分离卷积用于捕捉空间特征最后又是一个1x1的卷积来恢复通道数。此外它还包含一个SE模块Squeeze-and-Excitation用于通过学习重要通道的权重来提高网络的表示能力。Fused-MBConv与MBConv类似这种结构也包含了SE模块和1x1的卷积但它将深度可分离卷积替换为了一个标准的3x3卷积这通常可以减少运算量并提高性能。这两种结构通常用于构建高效的深度学习模型特别是在计算资源有限的情况下。Fused-MBConv因为其结构简会带来计算效率的提升。三、EfficientNetV2的核心代码核心代码使用方式看章节四import copy from functools import partial from collections import OrderedDict from torch import nn import os import re import subprocess from pathlib import Path import numpy as np import torch __all__ [efficientnet_v2] def get_efficientnet_v2_structure(model_name): if efficientnet_v2_s in model_name: return [ # e k s in out xN se fused (1, 3, 1, 24, 24, 2, False, True), (4, 3, 2, 24, 48, 4, False, True), (4, 3, 2, 48, 64, 4, False, True), (4, 3, 2, 64, 128, 6, True, False), (6, 3, 1, 128, 160, 9, True, False), (6, 3, 2, 160, 256, 15, True, False), ] elif efficientnet_v2_m in model_name: return [ # e k s in out xN se fused (1, 3, 1, 24, 24, 3, False, True), (4, 3, 2, 24, 48, 5, False, True), (4, 3, 2, 48, 80, 5, False, True), (4, 3, 2, 80, 160, 7, True, False), (6, 3, 1, 160, 176, 14, True, False), (6, 3, 2, 176, 304, 18, True, False), (6, 3, 1, 304, 512, 5, True, False), ] elif efficientnet_v2_l in model_name: return [ # e k s in out xN se fused (1, 3, 1, 32, 32, 4, False, True), (4, 3, 2, 32, 64, 7, False, True), (4, 3, 2, 64, 96, 7, False, True), (4, 3, 2, 96, 192, 10, True, False), (6, 3, 1, 192, 224, 19, True, False), (6, 3, 2, 224, 384, 25, True, False), (6, 3, 1, 384, 640, 7, True, False), ] elif efficientnet_v2_xl in model_name: return [ # e k s in out xN se fused (1, 3, 1, 32, 32, 4, False, True), (4, 3, 2, 32, 64, 8, False, True), (4, 3, 2, 64, 96, 8, False, True), (4, 3, 2, 96, 192, 16, True, False), (6, 3, 1, 192, 256, 24, True, False), (6, 3, 2, 256, 512, 32, True, False), (6, 3, 1, 512, 640, 8, True, False), ] class ConvBNAct(nn.Sequential): Convolution-Normalization-Activation Module def __init__(self, in_channel, out_channel, kernel_size, stride, groups, norm_layer, act, conv_layernn.Conv2d): super(ConvBNAct, self).__init__( conv_layer(in_channel, out_channel, kernel_size, stridestride, padding(kernel_size-1)//2, groupsgroups, biasFalse), norm_layer(out_channel), act() ) class SEUnit(nn.Module): Squeeze-Excitation Unit paper: https://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper def __init__(self, in_channel, reduction_ratio4, act1partial(nn.SiLU, inplaceTrue), act2nn.Sigmoid): super(SEUnit, self).__init__() hidden_dim in_channel // reduction_ratio self.avg_pool nn.AdaptiveAvgPool2d((1, 1)) self.fc1 nn.Conv2d(in_channel, hidden_dim, (1, 1), biasTrue) self.fc2 nn.Conv2d(hidden_dim, in_channel, (1, 1), biasTrue) self.act1 act1() self.act2 act2() def forward(self, x): return x * self.act2(self.fc2(self.act1(self.fc1(self.avg_pool(x))))) class StochasticDepth(nn.Module): StochasticDepth paper: https://link.springer.com/chapter/10.1007/978-3-319-46493-0_39 :arg - prob: Probability of dying - mode: row or all. row means that each row survives with different probability def __init__(self, prob, mode): super(StochasticDepth, self).__init__() self.prob prob self.survival 1.0 - prob self.mode mode def forward(self, x): if self.prob 0.0 or not self.training: return x else: shape [x.size(0)] [1] * (x.ndim - 1) if self.mode row else [1] return x * torch.empty(shape).bernoulli_(self.survival).div_(self.survival).to(x.device) class MBConvConfig: EfficientNet Building block configuration def __init__(self, expand_ratio: float, kernel: int, stride: int, in_ch: int, out_ch: int, layers: int, use_se: bool, fused: bool, actnn.SiLU, norm_layernn.BatchNorm2d): self.expand_ratio expand_ratio self.kernel kernel self.stride stride self.in_ch in_ch self.out_ch out_ch self.num_layers layers self.act act self.norm_layer norm_layer self.use_se use_se self.fused fused staticmethod def adjust_channels(channel, factor, divisible8): new_channel channel * factor divisible_channel max(divisible, (int(new_channel divisible / 2) // divisible) * divisible) divisible_channel divisible if divisible_channel 0.9 * new_channel else 0 return divisible_channel class MBConv(nn.Module): EfficientNet main building blocks :arg - c: MBConvConfig instance - sd_prob: stochastic path probability def __init__(self, c, sd_prob0.0): super(MBConv, self).__init__() inter_channel c.adjust_channels(c.in_ch, c.expand_ratio) block [] if c.expand_ratio 1: block.append((fused, ConvBNAct(c.in_ch, inter_channel, c.kernel, c.stride, 1, c.norm_layer, c.act))) elif c.fused: block.append((fused, ConvBNAct(c.in_ch, inter_channel, c.kernel, c.stride, 1, c.norm_layer, c.act))) block.append((fused_point_wise, ConvBNAct(inter_channel, c.out_ch, 1, 1, 1, c.norm_layer, nn.Identity))) else: block.append((linear_bottleneck, ConvBNAct(c.in_ch, inter_channel, 1, 1, 1, c.norm_layer, c.act))) block.append((depth_wise, ConvBNAct(inter_channel, inter_channel, c.kernel, c.stride, inter_channel, c.norm_layer, c.act))) block.append((se, SEUnit(inter_channel, 4 * c.expand_ratio))) block.append((point_wise, ConvBNAct(inter_channel, c.out_ch, 1, 1, 1, c.norm_layer, nn.Identity))) self.block nn.Sequential(OrderedDict(block)) self.use_skip_connection c.stride 1 and c.in_ch c.out_ch self.stochastic_path StochasticDepth(sd_prob, row) def forward(self, x): out self.block(x) if self.use_skip_connection: out x self.stochastic_path(out) return out def _make_divisible(v, divisor, min_valueNone): This function is taken from the original tf repo. It ensures that all layers have a channel number that is divisible by 8 It can be seen here: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py :param v: :param divisor: :param min_value: :return: if min_value is None: min_value divisor new_v max(min_value, int(v divisor / 2) // divisor * divisor) # Make sure that round down does not go down by more than 10%. if new_v 0.9 * v: new_v divisor return new_v class EfficientNetV2(nn.Module): Pytorch Implementation of EfficientNetV2 paper: https://arxiv.org/abs/2104.00298 - reference 1 (pytorch): https://github.com/d-li14/efficientnetv2.pytorch/blob/main/effnetv2.py - reference 2 (official): https://github.com/google/automl/blob/master/efficientnetv2/effnetv2_configs.py :arg - layer_infos: list of MBConvConfig - out_channels: bottleneck channel - nlcass: number of class - dropout: dropout probability before classifier layer - stochastic depth: stochastic depth probability def __init__(self, factor, depth, layer_infos, nclass0, dropout0.2, stochastic_depth0.0, blockMBConv, act_layernn.SiLU, norm_layernn.BatchNorm2d): super(EfficientNetV2, self).__init__() for layer in layer_infos: layer.in_ch _make_divisible(int(layer.in_ch * factor), 8) layer.out_ch _make_divisible(int(layer.out_ch * factor), 8) layer.num_layers max(1, int(layer.num_layers * depth)) self.layer_infos layer_infos self.norm_layer norm_layer self.act act_layer self.in_channel layer_infos[0].in_ch self.final_stage_channel layer_infos[-1].out_ch self.cur_block 0 self.num_block sum(stage.num_layers for stage in layer_infos) self.stochastic_depth stochastic_depth self.stem ConvBNAct(3, self.in_channel, 3, 2, 1, self.norm_layer, self.act) self.blocks nn.Sequential(*self.make_stages(layer_infos, block)) self.width_list [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))] def make_stages(self, layer_infos, block): return [layer for layer_info in layer_infos for layer in self.make_layers(copy.copy(layer_info), block)] def make_layers(self, layer_info, block): layers [] for i in range(layer_info.num_layers): layers.append(block(layer_info, sd_probself.get_sd_prob())) layer_info.in_ch layer_info.out_ch layer_info.stride 1 return layers def get_sd_prob(self): sd_prob self.stochastic_depth * (self.cur_block / self.num_block) self.cur_block 1 return sd_prob def forward(self, x): x self.stem(x) unique_tensors {} for idx, block in enumerate(self.blocks): x block(x) width, height x.shape[2], x.shape[3] unique_tensors[(width, height)] x result_list list(unique_tensors.values())[-4:] return result_list def efficientnet_v2_init(model): for m in model.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, modefan_out) if m.bias is not None: nn.init.zeros_(m.bias) elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)): nn.init.ones_(m.weight) nn.init.zeros_(m.bias) elif isinstance(m, nn.Linear): nn.init.normal_(m.weight, mean0.0, std0.01) nn.init.zeros_(m.bias) model_urls { efficientnet_v2_s: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-s.npy, efficientnet_v2_m: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-m.npy, efficientnet_v2_l: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-l.npy, efficientnet_v2_s_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-s-21k.npy, efficientnet_v2_m_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-m-21k.npy, efficientnet_v2_l_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-l-21k.npy, efficientnet_v2_xl_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-xl-21k.npy, } def load_from_zoo(model, model_name, pretrained_pathpretrained/official): Path(os.path.join(pretrained_path, model_name)).mkdir(parentsTrue, exist_okTrue) file_name os.path.join(pretrained_path, model_name, os.path.basename(model_urls[model_name])) load_npy(model, load_npy_from_url(urlmodel_urls[model_name], file_namefile_name)) def load_npy_from_url(url, file_name): if not Path(file_name).exists(): subprocess.run([wget, -r, -nc, -O, file_name, url]) return np.load(file_name, allow_pickleTrue).item() def npz_dim_convertor(name, weight): weight torch.from_numpy(weight) if kernel in name: if weight.dim() 4: if weight.shape[3] 1: # depth-wise convolution h w in_c out_c - in_c out_c h w weight torch.permute(weight, (2, 3, 0, 1)) else: # h w in_c out_c - out_c in_c h w weight torch.permute(weight, (3, 2, 0, 1)) elif weight.dim() 2: weight weight.transpose(1, 0) elif scale in name or bias in name: weight weight.squeeze() return weight def load_npy(model, weight): name_convertor [ # stem (stem.0.weight, stem/conv2d/kernel/ExponentialMovingAverage), (stem.1.weight, stem/tpu_batch_normalization/gamma/ExponentialMovingAverage), (stem.1.bias, stem/tpu_batch_normalization/beta/ExponentialMovingAverage), (stem.1.running_mean, stem/tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (stem.1.running_var, stem/tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # fused layer (block.fused.0.weight, conv2d/kernel/ExponentialMovingAverage), (block.fused.1.weight, tpu_batch_normalization/gamma/ExponentialMovingAverage), (block.fused.1.bias, tpu_batch_normalization/beta/ExponentialMovingAverage), (block.fused.1.running_mean, tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (block.fused.1.running_var, tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # linear bottleneck (block.linear_bottleneck.0.weight, conv2d/kernel/ExponentialMovingAverage), (block.linear_bottleneck.1.weight, tpu_batch_normalization/gamma/ExponentialMovingAverage), (block.linear_bottleneck.1.bias, tpu_batch_normalization/beta/ExponentialMovingAverage), (block.linear_bottleneck.1.running_mean, tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (block.linear_bottleneck.1.running_var, tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # depth wise layer (block.depth_wise.0.weight, depthwise_conv2d/depthwise_kernel/ExponentialMovingAverage), (block.depth_wise.1.weight, tpu_batch_normalization_1/gamma/ExponentialMovingAverage), (block.depth_wise.1.bias, tpu_batch_normalization_1/beta/ExponentialMovingAverage), (block.depth_wise.1.running_mean, tpu_batch_normalization_1/moving_mean/ExponentialMovingAverage), (block.depth_wise.1.running_var, tpu_batch_normalization_1/moving_variance/ExponentialMovingAverage), # se layer (block.se.fc1.weight, se/conv2d/kernel/ExponentialMovingAverage), (block.se.fc1.bias, se/conv2d/bias/ExponentialMovingAverage), (block.se.fc2.weight, se/conv2d_1/kernel/ExponentialMovingAverage), (block.se.fc2.bias, se/conv2d_1/bias/ExponentialMovingAverage), # point wise layer (block.fused_point_wise.0.weight, conv2d_1/kernel/ExponentialMovingAverage), (block.fused_point_wise.1.weight, tpu_batch_normalization_1/gamma/ExponentialMovingAverage), (block.fused_point_wise.1.bias, tpu_batch_normalization_1/beta/ExponentialMovingAverage), (block.fused_point_wise.1.running_mean, tpu_batch_normalization_1/moving_mean/ExponentialMovingAverage), (block.fused_point_wise.1.running_var, tpu_batch_normalization_1/moving_variance/ExponentialMovingAverage), (block.point_wise.0.weight, conv2d_1/kernel/ExponentialMovingAverage), (block.point_wise.1.weight, tpu_batch_normalization_2/gamma/ExponentialMovingAverage), (block.point_wise.1.bias, tpu_batch_normalization_2/beta/ExponentialMovingAverage), (block.point_wise.1.running_mean, tpu_batch_normalization_2/moving_mean/ExponentialMovingAverage), (block.point_wise.1.running_var, tpu_batch_normalization_2/moving_variance/ExponentialMovingAverage), # head (head.bottleneck.0.weight, head/conv2d/kernel/ExponentialMovingAverage), (head.bottleneck.1.weight, head/tpu_batch_normalization/gamma/ExponentialMovingAverage), (head.bottleneck.1.bias, head/tpu_batch_normalization/beta/ExponentialMovingAverage), (head.bottleneck.1.running_mean, head/tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (head.bottleneck.1.running_var, head/tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # classifier (head.classifier.weight, head/dense/kernel/ExponentialMovingAverage), (head.classifier.bias, head/dense/bias/ExponentialMovingAverage), (\\.(\\d)\\., lambda x: f_{int(x.group(1))}/), ] for name, param in list(model.named_parameters()) list(model.named_buffers()): for pattern, sub in name_convertor: name re.sub(pattern, sub, name) if dense/kernel in name and list(param.shape) not in [[1000, 1280], [21843, 1280]]: continue if dense/bias in name and list(param.shape) not in [[1000], [21843]]: continue if num_batches_tracked in name: continue param.data.copy_(npz_dim_convertor(name, weight.get(name))) def efficientnet_v2(model_nameefficientnet_v2_s, factor0.5, depth0.5, pretrainedFalse, nclass0, dropout0.1, stochastic_depth0.2, **kwargs): residual_config [MBConvConfig(*layer_config) for layer_config in get_efficientnet_v2_structure(model_name)] model EfficientNetV2(factor, depth, residual_config, nclass, dropoutdropout, stochastic_depthstochastic_depth, blockMBConv, act_layernn.SiLU) efficientnet_v2_init(model) if pretrained: load_from_zoo(model, model_name) return model if __name__ __main__: # Generating Sample image image_size (1, 3, 640, 640) image torch.rand(*image_size) # Model model efficientnet_v2(efficientnet_v2_s) out model(image) print(len(out))四、手把手教你添加EfficientNetV2机制4.1 修改一我们复制网络结构代码到“ultralytics/nn”目录下创建一个py文件复制粘贴进去 。4.2 修改二第二步我们在该目录下创建一个新的py文件名字为__init__.py(用群内的文件的话已经有了无需新建)然后在其内部导入我们的检测头如下图所示。4.3 修改三第三步我门中到如下文件ultralytics/nn/tasks.py进行导入和注册我们的模块(用群内的文件的话已经有了无需重新导入直接开始第四步即可)从今天开始以后的教程就都统一成这个样子了因为我默认大家用了我群内的文件来进行修改4.4 修改四添加如下两行代码4.5 修改五找到1600多行大概把具体看图片按照图片来修改就行添加红框内的部分注意没有()只是函数名我这里只添加了部分的版本这个还有更多的版本可以添加可以看后面章节五看我给的代码函数头即可。elif m in {自行添加对应的模型即可下面都是一样的}: m m(*args) c2 m.width_list # 返回通道列表 backbone True4.6 修改六按图修改。if isinstance(c2, list): m_ m m_.backbone True else: m_ nn.Sequential(*(m(*args) for _ in range(n))) if n 1 else m(*args) # module t str(m)[8:-2].replace(__main__., ) # module type m.np sum(x.numel() for x in m_.parameters()) # number params m_.i, m_.f, m_.type i 4 if backbone else i, f, t # attach index, from index, type4.7 修改七如下的也需要修改全部按照我的来。代码如下把原先的代码替换了即可。if verbose: LOGGER.info(f{i:3}{str(f):20}{n_:3}{m.np:10.0f} {t:45}{str(args):30}) # print save.extend(x % (i 4 if backbone else i) for x in ([f] if isinstance(f, int) else f) if x ! -1) # append to savelist layers.append(m_) if i 0: ch [] if isinstance(c2, list): ch.extend(c2) if len(c2) ! 5: ch.insert(0, 0) else: ch.append(c2)4.8 修改八修改七和前面的都不太一样需要修改前向传播中的一个部分 已经离开了parse_model方法了。可以在图片中看代码行数没有离开task.py文件都是同一个文件。 同时这个部分有好几个前向传播都很相似大家不要看错了是160多行左右的不同仓库版本可能有些差异同时我后面提供了代码大家直接复制粘贴即可不会修改联系博主获取视频教程。代码如下-def _predict_once(self, x, profileFalse, visualizeFalse, embedNone): Perform a forward pass through the network. Args: x (torch.Tensor): The input tensor to the model. profile (bool): Print the computation time of each layer if True. visualize (bool): Save the feature maps of the model if True. embed (list, optional): A list of layer indices to return embeddings from. Returns: (torch.Tensor): The last output of the model. y, dt, embeddings [], [], [] # outputs embed frozenset(embed) if embed is not None else {-1} max_idx max(embed) for m in self.model: if m.f ! -1: # if not from previous layer x y[m.f] if isinstance(m.f, int) else [x if j -1 else y[j] for j in m.f] # from earlier layers if profile: self._profile_one_layer(m, x, dt) if hasattr(m, backbone): x m(x) if len(x) ! 5: # 0 - 5 x.insert(0, None) for index, i in enumerate(x): if index in self.save: y.append(i) else: y.append(None) x x[-1] # 最后一个输出传给下一层 else: x m(x) # run y.append(x if m.i in self.save else None) # save output if visualize: feature_visualization(x, m.type, m.i, save_dirvisualize) if embed and m.i in embed: embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1)) # flatten if m.i max_idx: return torch.unbind(torch.cat(embeddings, 1), dim0) return x4.9 修改九我们找到如下文件ultralytics/utils/torch_utils.py按照如下的图片进行修改否则容易打印不出来计算量。五、EfficientNetV2的yaml文件5.1 EfficientNetV2的yaml文件训练信息YOLO26-Backbone-EfficientNetV2 summary: 443 layers, 2,008,088 parameters, 2,008,088 gradients, 4.6 GFLOPs# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # 下面 [-1, 1, efficientnet_v2}, [efficientnet_v2_s, 0.250.5]] 参数位置的0.25是通道放缩的系数, YOLOv11N是0.25 YOLOv11S是0.5 YOLOv11M是1. YOLOv11l是1 YOLOv11是1.5大家根据自己训练的YOLO版本设定即可. # 0.5对应的是模型的深度系数 # efficientnet-b0为模型的版本 # 支持的版本: # efficientnet_v2_s, efficientnet_v2_m, efficientnet_v2_l, efficientnet_v2_xl, # YOLO26 backbone backbone: # [from, repeats, module, args] - [-1, 1, efficientnet_v2, [efficientnet_v2_s, 0.25, 0.50]] # 0-4 P1/2 这里是四层大家不要被yaml文件限制住了思维不会画图进群看视频. # 注意args位置的参数对应模型的通道放缩系数width在上面scales位置, 假设你用yolov26n那么可以设置0.25 如果你用yolov26s可以设置0.5 # 0.5对应的是模型的深度系数 - [-1, 1, SPPF, [1024, 5, 3, True]] # 5 - [-1, 2, C2PSA, [1024]] # 6 # YOLO26 head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 3], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 9 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 2], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 12 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 9], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 15 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 6], 1, Concat, [1]] # cat head P5 - [-1, 2, C3k2, [1024, True, 0.5, True]] # 18 (P5/32-large) - [[12, 15, 18], 1, Detect, [nc]] # Detect(P3, P4, P5)5.2 训练文件的代码可以复制我的运行文件进行运行。import warnings warnings.filterwarnings(ignore) from ultralytics import YOLO if __name__ __main__: model YOLO(yolov8-MLLA.yaml) # 如何切换模型版本, 上面的ymal文件可以改为 yolov8s.yaml就是使用的v8s, # 类似某个改进的yaml文件名称为yolov8-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolov8l-XXX.yaml即可改的是上面YOLO中间的名字不是配置文件的 # model.load(yolov8n.pt) # 是否加载预训练权重,科研不建议大家加载否则很难提升精度 model.train(datarC:\Users\Administrator\PycharmProjects\yolov5-master\yolov5-master\Construction Site Safety.v30-raw-images_latestversion.yolov8\data.yaml, # 如果大家任务是其它的ultralytics/cfg/default.yaml找到这里修改task可以改成detect, segment, classify, pose cacheFalse, imgsz640, epochs150, single_clsFalse, # 是否是单类别检测 batch16, close_mosaic0, workers0, device0, optimizerSGD, # using SGD # resumeruns/train/exp21/weights/last.pt, # 如过想续训就设置last.pt的地址 ampTrue, # 如果出现训练损失为Nan可以关闭amp projectruns/train, nameexp, )六、成功运行记录下面是成功运行的截图已经完成了有1个epochs的训练图片太大截不全第2个epochs了。七、本文总结到此本文的正式分享内容就结束了在这里给大家推荐我的YOLOv26改进有效涨点专栏本专栏目前为新开的平均质量分98分后期我会根据各种最新的前沿顶会进行论文复现也会对一些老的改进机制进行补充如果大家觉得本文帮助到你了订阅本专栏关注后续更多的更新~专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制
开始正文前先向大家推荐我的YOLO专栏系列。本人持续更新 YOLOv8、YOLO11、YOLO26 等热门模型内容覆盖图像分类、目标检测、实例分割、多目标跟踪、姿态估计与关键点检测重点讲解 小目标检测、注意力机制、特征融合、损失函数改进、自定义数据集训练、消融实验及论文代码复现。同时分享如何使用 OpenAI Codex辅助撰写论文、配置实验环境、调试项目、改进模型和分析实验结果。 专栏目前正在进行限时优惠每周更新 5–7篇最新论文机制、YOLO改进方法和实战教程。订阅后可获得包含本人全部改进方案的代码与配置文件并加入专属技术交流群。我也会定期在群内分享 YOLO论文选题、创新点设计、实验方案、论文写作与投稿发表经验欢迎大家订阅交流一、本文介绍这次给大家带来的改进机制是高效主干网络——EfficientNetV2本文将使用该网络替换YOLOv26原有的特征提取网络。EfficientNetV2在EfficientNetV1复合缩放策略的基础上进一步针对模型训练速度和计算效率进行了优化其不仅继续兼顾网络深度、通道宽度和输入分辨率还引入了更加高效的Fused-MBConv结构在网络浅层使用普通卷积融合原有MBConv中的扩展卷积和深度卷积以减少部分设备上的访存开销并提高实际运行效率。同时EfficientNetV2提出了改进的渐进式学习策略在训练过程中逐步增大输入图像尺寸并根据图像尺寸自适应调整数据增强和正则化强度从而在保持模型精度的同时加快训练收敛。相较于V1版本EfficientNetV2的主要改进集中在训练速度、参数效率和硬件运行性能方面不过经过本人实际测试当前使用的V2版本速度并没有明显快于V1部分情况下甚至更慢这可能与所选择的模型规模、输入尺寸、硬件平台以及部署环境不同有关因此建议大家选择参数量和计算量接近的版本进行公平对比。EfficientNetV2同样提供S、M、L等多种规模大家可以根据显存条件、数据集难度和实际任务需求在源码中灵活选择。本文将首先介绍EfficientNetV2的整体框架、Fused-MBConv和渐进式学习策略随后结合完整代码与配置文件手把手讲解如何完成模块注册、网络配置以及YOLOv26特征提取网络的替换。本文内容可根据yolov11的N、S、M、L、X进行二次缩放轻量化更上一层。专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制目录一、本文介绍二、EfficientNetV2的框架原理三、EfficientNetV2的核心代码四、手把手教你添加EfficientNetV2机制4.1 修改一4.2 修改二4.3 修改三4.4 修改四4.5 修改五4.6 修改六4.7 修改七4.8 修改八4.9 修改九五、EfficientNetV2的yaml文件5.1 EfficientNetV2的yaml文件5.2 训练文件的代码六、成功运行记录七、本文总结二、EfficientNetV2的框架原理官方论文地址官方论文地址点击即可跳转官方代码地址官方代码地址点击即可跳转这篇论文主要介绍了EfficientNetV2这是一种新型的卷积神经网络它的特点是训练速度更快、参数效率更高。通过结合训练感知的神经架构搜索和缩放这些模型在训练速度和参数效率上都得到了优化。文章还提出了一种改进的渐进式学习方法通过在训练过程中逐步增加图像尺寸并适应性调整正则化来加快训练速度同时保持准确性。EfficientNetV2的主要创新点包括1. 结构创新EfficientNetV2在早期层中采用了fused-MBConv结构这有助于降低内存访问开销。此外EfficientNetV2倾向于使用较小的扩展比例和3x3的卷积核大小同时增加更多的层次来补偿由于使用较小卷积核导致的接收域减小。最后EfficientNetV2完全移除了原始EfficientNet中的最后一个stride-1阶段可能是因为它的大参数尺寸和内存访问开销。2. 训练速度的优化您的研究比较了EfficientNetV2与其他模型在固定图像大小下的训练步骤时间。EfficientNetV2通过训练感知的神经架构搜索和模型缩放实现了比其他最新模型更快的训练速度。3.渐进式学习与自适应正则化EfficientNetV2采用了改进的渐进式学习方法该方法在训练早期使用较小的图像尺寸和较弱的正则化使得网络可以更容易、更快地学习简单的表示。随着训练的进行逐渐增加图像尺寸并通过增强正则化来提高学习难度。4. 自适应正则化的重要性您的研究强调了自适应正则化的重要性这种方法根据图像大小动态调整正则化强度。该方法简单但有效并且可以与其他方法结合使用。图片展示了两种卷积神经网络中的模块MBConv和Fused-MBConv的结构。MBConv这是一种包含了深度可分离卷积depthwise conv3x3的模块其包括1x1的卷积用于调整通道数随后是深度可分离卷积用于捕捉空间特征最后又是一个1x1的卷积来恢复通道数。此外它还包含一个SE模块Squeeze-and-Excitation用于通过学习重要通道的权重来提高网络的表示能力。Fused-MBConv与MBConv类似这种结构也包含了SE模块和1x1的卷积但它将深度可分离卷积替换为了一个标准的3x3卷积这通常可以减少运算量并提高性能。这两种结构通常用于构建高效的深度学习模型特别是在计算资源有限的情况下。Fused-MBConv因为其结构简会带来计算效率的提升。三、EfficientNetV2的核心代码核心代码使用方式看章节四import copy from functools import partial from collections import OrderedDict from torch import nn import os import re import subprocess from pathlib import Path import numpy as np import torch __all__ [efficientnet_v2] def get_efficientnet_v2_structure(model_name): if efficientnet_v2_s in model_name: return [ # e k s in out xN se fused (1, 3, 1, 24, 24, 2, False, True), (4, 3, 2, 24, 48, 4, False, True), (4, 3, 2, 48, 64, 4, False, True), (4, 3, 2, 64, 128, 6, True, False), (6, 3, 1, 128, 160, 9, True, False), (6, 3, 2, 160, 256, 15, True, False), ] elif efficientnet_v2_m in model_name: return [ # e k s in out xN se fused (1, 3, 1, 24, 24, 3, False, True), (4, 3, 2, 24, 48, 5, False, True), (4, 3, 2, 48, 80, 5, False, True), (4, 3, 2, 80, 160, 7, True, False), (6, 3, 1, 160, 176, 14, True, False), (6, 3, 2, 176, 304, 18, True, False), (6, 3, 1, 304, 512, 5, True, False), ] elif efficientnet_v2_l in model_name: return [ # e k s in out xN se fused (1, 3, 1, 32, 32, 4, False, True), (4, 3, 2, 32, 64, 7, False, True), (4, 3, 2, 64, 96, 7, False, True), (4, 3, 2, 96, 192, 10, True, False), (6, 3, 1, 192, 224, 19, True, False), (6, 3, 2, 224, 384, 25, True, False), (6, 3, 1, 384, 640, 7, True, False), ] elif efficientnet_v2_xl in model_name: return [ # e k s in out xN se fused (1, 3, 1, 32, 32, 4, False, True), (4, 3, 2, 32, 64, 8, False, True), (4, 3, 2, 64, 96, 8, False, True), (4, 3, 2, 96, 192, 16, True, False), (6, 3, 1, 192, 256, 24, True, False), (6, 3, 2, 256, 512, 32, True, False), (6, 3, 1, 512, 640, 8, True, False), ] class ConvBNAct(nn.Sequential): Convolution-Normalization-Activation Module def __init__(self, in_channel, out_channel, kernel_size, stride, groups, norm_layer, act, conv_layernn.Conv2d): super(ConvBNAct, self).__init__( conv_layer(in_channel, out_channel, kernel_size, stridestride, padding(kernel_size-1)//2, groupsgroups, biasFalse), norm_layer(out_channel), act() ) class SEUnit(nn.Module): Squeeze-Excitation Unit paper: https://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper def __init__(self, in_channel, reduction_ratio4, act1partial(nn.SiLU, inplaceTrue), act2nn.Sigmoid): super(SEUnit, self).__init__() hidden_dim in_channel // reduction_ratio self.avg_pool nn.AdaptiveAvgPool2d((1, 1)) self.fc1 nn.Conv2d(in_channel, hidden_dim, (1, 1), biasTrue) self.fc2 nn.Conv2d(hidden_dim, in_channel, (1, 1), biasTrue) self.act1 act1() self.act2 act2() def forward(self, x): return x * self.act2(self.fc2(self.act1(self.fc1(self.avg_pool(x))))) class StochasticDepth(nn.Module): StochasticDepth paper: https://link.springer.com/chapter/10.1007/978-3-319-46493-0_39 :arg - prob: Probability of dying - mode: row or all. row means that each row survives with different probability def __init__(self, prob, mode): super(StochasticDepth, self).__init__() self.prob prob self.survival 1.0 - prob self.mode mode def forward(self, x): if self.prob 0.0 or not self.training: return x else: shape [x.size(0)] [1] * (x.ndim - 1) if self.mode row else [1] return x * torch.empty(shape).bernoulli_(self.survival).div_(self.survival).to(x.device) class MBConvConfig: EfficientNet Building block configuration def __init__(self, expand_ratio: float, kernel: int, stride: int, in_ch: int, out_ch: int, layers: int, use_se: bool, fused: bool, actnn.SiLU, norm_layernn.BatchNorm2d): self.expand_ratio expand_ratio self.kernel kernel self.stride stride self.in_ch in_ch self.out_ch out_ch self.num_layers layers self.act act self.norm_layer norm_layer self.use_se use_se self.fused fused staticmethod def adjust_channels(channel, factor, divisible8): new_channel channel * factor divisible_channel max(divisible, (int(new_channel divisible / 2) // divisible) * divisible) divisible_channel divisible if divisible_channel 0.9 * new_channel else 0 return divisible_channel class MBConv(nn.Module): EfficientNet main building blocks :arg - c: MBConvConfig instance - sd_prob: stochastic path probability def __init__(self, c, sd_prob0.0): super(MBConv, self).__init__() inter_channel c.adjust_channels(c.in_ch, c.expand_ratio) block [] if c.expand_ratio 1: block.append((fused, ConvBNAct(c.in_ch, inter_channel, c.kernel, c.stride, 1, c.norm_layer, c.act))) elif c.fused: block.append((fused, ConvBNAct(c.in_ch, inter_channel, c.kernel, c.stride, 1, c.norm_layer, c.act))) block.append((fused_point_wise, ConvBNAct(inter_channel, c.out_ch, 1, 1, 1, c.norm_layer, nn.Identity))) else: block.append((linear_bottleneck, ConvBNAct(c.in_ch, inter_channel, 1, 1, 1, c.norm_layer, c.act))) block.append((depth_wise, ConvBNAct(inter_channel, inter_channel, c.kernel, c.stride, inter_channel, c.norm_layer, c.act))) block.append((se, SEUnit(inter_channel, 4 * c.expand_ratio))) block.append((point_wise, ConvBNAct(inter_channel, c.out_ch, 1, 1, 1, c.norm_layer, nn.Identity))) self.block nn.Sequential(OrderedDict(block)) self.use_skip_connection c.stride 1 and c.in_ch c.out_ch self.stochastic_path StochasticDepth(sd_prob, row) def forward(self, x): out self.block(x) if self.use_skip_connection: out x self.stochastic_path(out) return out def _make_divisible(v, divisor, min_valueNone): This function is taken from the original tf repo. It ensures that all layers have a channel number that is divisible by 8 It can be seen here: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py :param v: :param divisor: :param min_value: :return: if min_value is None: min_value divisor new_v max(min_value, int(v divisor / 2) // divisor * divisor) # Make sure that round down does not go down by more than 10%. if new_v 0.9 * v: new_v divisor return new_v class EfficientNetV2(nn.Module): Pytorch Implementation of EfficientNetV2 paper: https://arxiv.org/abs/2104.00298 - reference 1 (pytorch): https://github.com/d-li14/efficientnetv2.pytorch/blob/main/effnetv2.py - reference 2 (official): https://github.com/google/automl/blob/master/efficientnetv2/effnetv2_configs.py :arg - layer_infos: list of MBConvConfig - out_channels: bottleneck channel - nlcass: number of class - dropout: dropout probability before classifier layer - stochastic depth: stochastic depth probability def __init__(self, factor, depth, layer_infos, nclass0, dropout0.2, stochastic_depth0.0, blockMBConv, act_layernn.SiLU, norm_layernn.BatchNorm2d): super(EfficientNetV2, self).__init__() for layer in layer_infos: layer.in_ch _make_divisible(int(layer.in_ch * factor), 8) layer.out_ch _make_divisible(int(layer.out_ch * factor), 8) layer.num_layers max(1, int(layer.num_layers * depth)) self.layer_infos layer_infos self.norm_layer norm_layer self.act act_layer self.in_channel layer_infos[0].in_ch self.final_stage_channel layer_infos[-1].out_ch self.cur_block 0 self.num_block sum(stage.num_layers for stage in layer_infos) self.stochastic_depth stochastic_depth self.stem ConvBNAct(3, self.in_channel, 3, 2, 1, self.norm_layer, self.act) self.blocks nn.Sequential(*self.make_stages(layer_infos, block)) self.width_list [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))] def make_stages(self, layer_infos, block): return [layer for layer_info in layer_infos for layer in self.make_layers(copy.copy(layer_info), block)] def make_layers(self, layer_info, block): layers [] for i in range(layer_info.num_layers): layers.append(block(layer_info, sd_probself.get_sd_prob())) layer_info.in_ch layer_info.out_ch layer_info.stride 1 return layers def get_sd_prob(self): sd_prob self.stochastic_depth * (self.cur_block / self.num_block) self.cur_block 1 return sd_prob def forward(self, x): x self.stem(x) unique_tensors {} for idx, block in enumerate(self.blocks): x block(x) width, height x.shape[2], x.shape[3] unique_tensors[(width, height)] x result_list list(unique_tensors.values())[-4:] return result_list def efficientnet_v2_init(model): for m in model.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, modefan_out) if m.bias is not None: nn.init.zeros_(m.bias) elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)): nn.init.ones_(m.weight) nn.init.zeros_(m.bias) elif isinstance(m, nn.Linear): nn.init.normal_(m.weight, mean0.0, std0.01) nn.init.zeros_(m.bias) model_urls { efficientnet_v2_s: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-s.npy, efficientnet_v2_m: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-m.npy, efficientnet_v2_l: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-l.npy, efficientnet_v2_s_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-s-21k.npy, efficientnet_v2_m_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-m-21k.npy, efficientnet_v2_l_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-l-21k.npy, efficientnet_v2_xl_in21k: https://github.com/hankyul2/EfficientNetV2-pytorch/releases/download/EfficientNetV2-pytorch/efficientnetv2-xl-21k.npy, } def load_from_zoo(model, model_name, pretrained_pathpretrained/official): Path(os.path.join(pretrained_path, model_name)).mkdir(parentsTrue, exist_okTrue) file_name os.path.join(pretrained_path, model_name, os.path.basename(model_urls[model_name])) load_npy(model, load_npy_from_url(urlmodel_urls[model_name], file_namefile_name)) def load_npy_from_url(url, file_name): if not Path(file_name).exists(): subprocess.run([wget, -r, -nc, -O, file_name, url]) return np.load(file_name, allow_pickleTrue).item() def npz_dim_convertor(name, weight): weight torch.from_numpy(weight) if kernel in name: if weight.dim() 4: if weight.shape[3] 1: # depth-wise convolution h w in_c out_c - in_c out_c h w weight torch.permute(weight, (2, 3, 0, 1)) else: # h w in_c out_c - out_c in_c h w weight torch.permute(weight, (3, 2, 0, 1)) elif weight.dim() 2: weight weight.transpose(1, 0) elif scale in name or bias in name: weight weight.squeeze() return weight def load_npy(model, weight): name_convertor [ # stem (stem.0.weight, stem/conv2d/kernel/ExponentialMovingAverage), (stem.1.weight, stem/tpu_batch_normalization/gamma/ExponentialMovingAverage), (stem.1.bias, stem/tpu_batch_normalization/beta/ExponentialMovingAverage), (stem.1.running_mean, stem/tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (stem.1.running_var, stem/tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # fused layer (block.fused.0.weight, conv2d/kernel/ExponentialMovingAverage), (block.fused.1.weight, tpu_batch_normalization/gamma/ExponentialMovingAverage), (block.fused.1.bias, tpu_batch_normalization/beta/ExponentialMovingAverage), (block.fused.1.running_mean, tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (block.fused.1.running_var, tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # linear bottleneck (block.linear_bottleneck.0.weight, conv2d/kernel/ExponentialMovingAverage), (block.linear_bottleneck.1.weight, tpu_batch_normalization/gamma/ExponentialMovingAverage), (block.linear_bottleneck.1.bias, tpu_batch_normalization/beta/ExponentialMovingAverage), (block.linear_bottleneck.1.running_mean, tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (block.linear_bottleneck.1.running_var, tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # depth wise layer (block.depth_wise.0.weight, depthwise_conv2d/depthwise_kernel/ExponentialMovingAverage), (block.depth_wise.1.weight, tpu_batch_normalization_1/gamma/ExponentialMovingAverage), (block.depth_wise.1.bias, tpu_batch_normalization_1/beta/ExponentialMovingAverage), (block.depth_wise.1.running_mean, tpu_batch_normalization_1/moving_mean/ExponentialMovingAverage), (block.depth_wise.1.running_var, tpu_batch_normalization_1/moving_variance/ExponentialMovingAverage), # se layer (block.se.fc1.weight, se/conv2d/kernel/ExponentialMovingAverage), (block.se.fc1.bias, se/conv2d/bias/ExponentialMovingAverage), (block.se.fc2.weight, se/conv2d_1/kernel/ExponentialMovingAverage), (block.se.fc2.bias, se/conv2d_1/bias/ExponentialMovingAverage), # point wise layer (block.fused_point_wise.0.weight, conv2d_1/kernel/ExponentialMovingAverage), (block.fused_point_wise.1.weight, tpu_batch_normalization_1/gamma/ExponentialMovingAverage), (block.fused_point_wise.1.bias, tpu_batch_normalization_1/beta/ExponentialMovingAverage), (block.fused_point_wise.1.running_mean, tpu_batch_normalization_1/moving_mean/ExponentialMovingAverage), (block.fused_point_wise.1.running_var, tpu_batch_normalization_1/moving_variance/ExponentialMovingAverage), (block.point_wise.0.weight, conv2d_1/kernel/ExponentialMovingAverage), (block.point_wise.1.weight, tpu_batch_normalization_2/gamma/ExponentialMovingAverage), (block.point_wise.1.bias, tpu_batch_normalization_2/beta/ExponentialMovingAverage), (block.point_wise.1.running_mean, tpu_batch_normalization_2/moving_mean/ExponentialMovingAverage), (block.point_wise.1.running_var, tpu_batch_normalization_2/moving_variance/ExponentialMovingAverage), # head (head.bottleneck.0.weight, head/conv2d/kernel/ExponentialMovingAverage), (head.bottleneck.1.weight, head/tpu_batch_normalization/gamma/ExponentialMovingAverage), (head.bottleneck.1.bias, head/tpu_batch_normalization/beta/ExponentialMovingAverage), (head.bottleneck.1.running_mean, head/tpu_batch_normalization/moving_mean/ExponentialMovingAverage), (head.bottleneck.1.running_var, head/tpu_batch_normalization/moving_variance/ExponentialMovingAverage), # classifier (head.classifier.weight, head/dense/kernel/ExponentialMovingAverage), (head.classifier.bias, head/dense/bias/ExponentialMovingAverage), (\\.(\\d)\\., lambda x: f_{int(x.group(1))}/), ] for name, param in list(model.named_parameters()) list(model.named_buffers()): for pattern, sub in name_convertor: name re.sub(pattern, sub, name) if dense/kernel in name and list(param.shape) not in [[1000, 1280], [21843, 1280]]: continue if dense/bias in name and list(param.shape) not in [[1000], [21843]]: continue if num_batches_tracked in name: continue param.data.copy_(npz_dim_convertor(name, weight.get(name))) def efficientnet_v2(model_nameefficientnet_v2_s, factor0.5, depth0.5, pretrainedFalse, nclass0, dropout0.1, stochastic_depth0.2, **kwargs): residual_config [MBConvConfig(*layer_config) for layer_config in get_efficientnet_v2_structure(model_name)] model EfficientNetV2(factor, depth, residual_config, nclass, dropoutdropout, stochastic_depthstochastic_depth, blockMBConv, act_layernn.SiLU) efficientnet_v2_init(model) if pretrained: load_from_zoo(model, model_name) return model if __name__ __main__: # Generating Sample image image_size (1, 3, 640, 640) image torch.rand(*image_size) # Model model efficientnet_v2(efficientnet_v2_s) out model(image) print(len(out))四、手把手教你添加EfficientNetV2机制4.1 修改一我们复制网络结构代码到“ultralytics/nn”目录下创建一个py文件复制粘贴进去 。4.2 修改二第二步我们在该目录下创建一个新的py文件名字为__init__.py(用群内的文件的话已经有了无需新建)然后在其内部导入我们的检测头如下图所示。4.3 修改三第三步我门中到如下文件ultralytics/nn/tasks.py进行导入和注册我们的模块(用群内的文件的话已经有了无需重新导入直接开始第四步即可)从今天开始以后的教程就都统一成这个样子了因为我默认大家用了我群内的文件来进行修改4.4 修改四添加如下两行代码4.5 修改五找到1600多行大概把具体看图片按照图片来修改就行添加红框内的部分注意没有()只是函数名我这里只添加了部分的版本这个还有更多的版本可以添加可以看后面章节五看我给的代码函数头即可。elif m in {自行添加对应的模型即可下面都是一样的}: m m(*args) c2 m.width_list # 返回通道列表 backbone True4.6 修改六按图修改。if isinstance(c2, list): m_ m m_.backbone True else: m_ nn.Sequential(*(m(*args) for _ in range(n))) if n 1 else m(*args) # module t str(m)[8:-2].replace(__main__., ) # module type m.np sum(x.numel() for x in m_.parameters()) # number params m_.i, m_.f, m_.type i 4 if backbone else i, f, t # attach index, from index, type4.7 修改七如下的也需要修改全部按照我的来。代码如下把原先的代码替换了即可。if verbose: LOGGER.info(f{i:3}{str(f):20}{n_:3}{m.np:10.0f} {t:45}{str(args):30}) # print save.extend(x % (i 4 if backbone else i) for x in ([f] if isinstance(f, int) else f) if x ! -1) # append to savelist layers.append(m_) if i 0: ch [] if isinstance(c2, list): ch.extend(c2) if len(c2) ! 5: ch.insert(0, 0) else: ch.append(c2)4.8 修改八修改七和前面的都不太一样需要修改前向传播中的一个部分 已经离开了parse_model方法了。可以在图片中看代码行数没有离开task.py文件都是同一个文件。 同时这个部分有好几个前向传播都很相似大家不要看错了是160多行左右的不同仓库版本可能有些差异同时我后面提供了代码大家直接复制粘贴即可不会修改联系博主获取视频教程。代码如下-def _predict_once(self, x, profileFalse, visualizeFalse, embedNone): Perform a forward pass through the network. Args: x (torch.Tensor): The input tensor to the model. profile (bool): Print the computation time of each layer if True. visualize (bool): Save the feature maps of the model if True. embed (list, optional): A list of layer indices to return embeddings from. Returns: (torch.Tensor): The last output of the model. y, dt, embeddings [], [], [] # outputs embed frozenset(embed) if embed is not None else {-1} max_idx max(embed) for m in self.model: if m.f ! -1: # if not from previous layer x y[m.f] if isinstance(m.f, int) else [x if j -1 else y[j] for j in m.f] # from earlier layers if profile: self._profile_one_layer(m, x, dt) if hasattr(m, backbone): x m(x) if len(x) ! 5: # 0 - 5 x.insert(0, None) for index, i in enumerate(x): if index in self.save: y.append(i) else: y.append(None) x x[-1] # 最后一个输出传给下一层 else: x m(x) # run y.append(x if m.i in self.save else None) # save output if visualize: feature_visualization(x, m.type, m.i, save_dirvisualize) if embed and m.i in embed: embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1)) # flatten if m.i max_idx: return torch.unbind(torch.cat(embeddings, 1), dim0) return x4.9 修改九我们找到如下文件ultralytics/utils/torch_utils.py按照如下的图片进行修改否则容易打印不出来计算量。五、EfficientNetV2的yaml文件5.1 EfficientNetV2的yaml文件训练信息YOLO26-Backbone-EfficientNetV2 summary: 443 layers, 2,008,088 parameters, 2,008,088 gradients, 4.6 GFLOPs# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # 下面 [-1, 1, efficientnet_v2}, [efficientnet_v2_s, 0.250.5]] 参数位置的0.25是通道放缩的系数, YOLOv11N是0.25 YOLOv11S是0.5 YOLOv11M是1. YOLOv11l是1 YOLOv11是1.5大家根据自己训练的YOLO版本设定即可. # 0.5对应的是模型的深度系数 # efficientnet-b0为模型的版本 # 支持的版本: # efficientnet_v2_s, efficientnet_v2_m, efficientnet_v2_l, efficientnet_v2_xl, # YOLO26 backbone backbone: # [from, repeats, module, args] - [-1, 1, efficientnet_v2, [efficientnet_v2_s, 0.25, 0.50]] # 0-4 P1/2 这里是四层大家不要被yaml文件限制住了思维不会画图进群看视频. # 注意args位置的参数对应模型的通道放缩系数width在上面scales位置, 假设你用yolov26n那么可以设置0.25 如果你用yolov26s可以设置0.5 # 0.5对应的是模型的深度系数 - [-1, 1, SPPF, [1024, 5, 3, True]] # 5 - [-1, 2, C2PSA, [1024]] # 6 # YOLO26 head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 3], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 9 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 2], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 12 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 9], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 15 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 6], 1, Concat, [1]] # cat head P5 - [-1, 2, C3k2, [1024, True, 0.5, True]] # 18 (P5/32-large) - [[12, 15, 18], 1, Detect, [nc]] # Detect(P3, P4, P5)5.2 训练文件的代码可以复制我的运行文件进行运行。import warnings warnings.filterwarnings(ignore) from ultralytics import YOLO if __name__ __main__: model YOLO(yolov8-MLLA.yaml) # 如何切换模型版本, 上面的ymal文件可以改为 yolov8s.yaml就是使用的v8s, # 类似某个改进的yaml文件名称为yolov8-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolov8l-XXX.yaml即可改的是上面YOLO中间的名字不是配置文件的 # model.load(yolov8n.pt) # 是否加载预训练权重,科研不建议大家加载否则很难提升精度 model.train(datarC:\Users\Administrator\PycharmProjects\yolov5-master\yolov5-master\Construction Site Safety.v30-raw-images_latestversion.yolov8\data.yaml, # 如果大家任务是其它的ultralytics/cfg/default.yaml找到这里修改task可以改成detect, segment, classify, pose cacheFalse, imgsz640, epochs150, single_clsFalse, # 是否是单类别检测 batch16, close_mosaic0, workers0, device0, optimizerSGD, # using SGD # resumeruns/train/exp21/weights/last.pt, # 如过想续训就设置last.pt的地址 ampTrue, # 如果出现训练损失为Nan可以关闭amp projectruns/train, nameexp, )六、成功运行记录下面是成功运行的截图已经完成了有1个epochs的训练图片太大截不全第2个epochs了。七、本文总结到此本文的正式分享内容就结束了在这里给大家推荐我的YOLOv26改进有效涨点专栏本专栏目前为新开的平均质量分98分后期我会根据各种最新的前沿顶会进行论文复现也会对一些老的改进机制进行补充如果大家觉得本文帮助到你了订阅本专栏关注后续更多的更新~专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制
